1 / 24

Review of Data Processing Steps

Review of Data Processing Steps. MICS3 Data Analysis and Report Writing Workshop. Step 1: Enter main data. Enter the main data Creates files such as hh001M.dat, hh002M.dat, etc. Step 2: Structure check. Run the check programs for each cluster to identify structure problems .

stevie
Download Presentation

Review of Data Processing Steps

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript


  1. Review of Data Processing Steps MICS3 Data Analysis and Report Writing Workshop

  2. Step 1: Enter main data Enter the main data Creates files such as hh001M.dat, hh002M.dat, etc.

  3. Step 2: Structure check • Run the check programs for each cluster to identify structure problems

  4. Step 3: Correct structure problems • Correct the identified structure problems

  5. Step 4: Verification • Assign verification to a second operator Creates files such as hh001V.dat, hh002v.dat, etc.

  6. Step 5: Compare data • Compare the main data and the verification data, and identify differences

  7. Step 6: Correct differences • Correct for differences in the two sets of data Corrections may have to be made either in the main data or verification data

  8. Step 7: Compare data • Compare main data and verification data again, and continue comparing and correcting as many times as needed, until there are no differences

  9. Step 8: Secondary editing • Run secondary editing

  10. Step 9: Correct problems • Correct all problems identified during secondary editing There may be some warnings you will not be able to correct for, make sure to document these

  11. Step 10: Export data • Export clean data files by using the “Export” procedure in the Supervisor’s Menu Creates 4 SPSS data files (mych.dat, myhh.dat, myhl.dat, mywm.dat) and 4 SPSS syntax files (mych.sps, myhh.sps, myhl.sps, mywm.sps) in the MICS\SPSS directory

  12. Step 11: Import data into SPSS • In SPSS, run my*.sps files The my*.sps files import the data into SPSS and create SPSS-format data files, with variable labels, value labels etc. At the end of each run, save your work in data files as hh.sav, hl.sav, wm.sav and ch.sav

  13. Step 12: Run frequency distributions • Open SPSS and run frequency distributions for all of the variables in all 4 files • Detect any unexpected codes or inconsistencies, and if necessary, return to CSPro and make corrections. Then, repeat step 10

  14. Step 13:Calculate weights • Obtain distribution of interview results by the unit based on which you intend to calculate unique sample weights: - using the weights_table.sps syntax file, if calculation at stratum level, e.g.regions and area - using the weights_table_alt.sps syntax file, if calculation at cluster level

  15. Calculate weights cont. • Calculate final sample weights • using weights.xls, if calculations are carried out at stratum level • weights_alt.xls, if calculations are carried out at at the cluster level

  16. Calculate weights cont. • Once calculations in weights.xls or weights_alt.xls have been completed, save the “Output” workbook as a .csv (comma separated file) • In SPSS, run weights.sps or weights_alt.sps to create an SPSS data file with the weights which will be saved as weights.sav

  17. Step 15: Append sample weights • Append sample weights to the exported SPSS files (hh.sav, hl.sav, wm.sav and ch.sav), by using the SPSS weights_merge.sps or weights_merge_alt.sps syntax file

  18. Step 16:Customize wealth.sps • Customize the wealth.sps syntax file that calculates wealth index values, together with the survey coordinator/technical manager, according to the items included in your questionnaire

  19. Step 17:Run and append wealth • Run the SPSS syntax from step 16to calculate wealth index values, and append these to the 4 exported data files, using the SPSS wealth_merge.sps syntax

  20. Step 18:Customize make*.sps • Customize the make*.sps syntax files, in accordance with the contents of your questionnaires. • Take out any variables and associated syntax which are not included in your questionnaire, or modify the variables according to your response categories (one example is categories of ethnicity)

  21. Step 19: Run make.sps • Run make.sps to recode all additional variables needed for the tabulations Make.sps is provided as a batch file which calls and runs each of the make*.sps files in turn

  22. Step 20: Customize each syntax • Customize all tabulation syntax filesin accordance with the contents of your survey • Delete the syntax which are used to obtain tables on topics which are not included in your survey

  23. Step 21:Run all tables.sps • Once all tabulation syntax files are customized and free of errors, customize all tables.sps all tables.sps calls and runs all tabulation syntax files, and produces an output which includes all tables If any of the tabulation syntax files have errors, the program will stop and you will have to correct the tabulation syntax file. Then re-run all tables.sps

  24. Ngagne Diakhate ndiakhate@unicef.org

More Related